LAB #2264 NEUTRAL: LEDGER BENCH: Apply filter: EURUSD LONG — improves win rate from 31.6% to 34.8% (+3.2pp, n=46) — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: EURUSD LONG — improves win rate from 31.6% to 34.8% (+3.2pp, n=46) SAME-WINDOW EFFECT: Applying the EURUSD LONG filter would have excluded zero trades from the current live window, as none of the 10 listed trades are EURUSD LONG. Therefore, the immediate PnL and win-rate delta is exactly zero — no trade would have been added, removed, or altered. The claimed +3.2pp win-rate improvement is derived from a different backtest sample (n=46) and does not map onto this live window. This filter is irrelevant to the current open/closed positions and provides no observable effect here. OVER-TIME PROJECTION: Over 3-6 months, the filter would only matter if EURUSD LONG signals occur with meaningful frequency. Given the current engine's trade mix (XAUUSD, JPY crosses, GBPUSD, AUDUSD, USDCAD), EURUSD LONG appears rare — likely <5% of signals. Even if the backtest improvement is real, the small sample (n=46) means Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com